Using Fictitious Class Representations to Boost Discriminative Zero-Shot Learners
arXiv:2111.13550
Abstract
Focusing on discriminative zero-shot learning, in this work we introduce a novel mechanism that dynamically augments during training the set of seen classes to produce additional fictitious classes. These fictitious classes diminish the model's tendency to fixate during training on attribute correlations that appear in the training set but will not appear in newly exposed classes. The proposed model is tested within the two formulations of the zero-shot learning framework; namely, generalized zero-shot learning (GZSL) and classical zero-shot learning (CZSL). Our model improves the state-of-the-art performance on the CUB dataset and reaches comparable results on the other common datasets, AWA2 and SUN. We investigate the strengths and weaknesses of our method, including the effects of catastrophic forgetting when training an end-to-end zero-shot model.
References in corpus (13)
- Overcoming catastrophic forgetting in neural networks
- Bootstrap your own latent: A new approach to self-supervised Learning
- An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
- Data Augmentation using Random Image Cropping and Patching for Deep CNNs
- Manifold Mixup: Better Representations by Interpolating Hidden States
- Deep Anomaly Detection Using Geometric Transformations
- FearNet: Brain-Inspired Model for Incremental Learning
- Measuring Catastrophic Forgetting in Neural Networks
- Semantic-Guided Multi-Attention Localization for Zero-Shot Learning
- Preserving Semantic Relations for Zero-Shot Learning
- Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
- Attribute Prototype Network for Zero-Shot Learning
- Goal-Oriented Gaze Estimation for Zero-Shot Learning